# Week 4 Data Visualization Lab
# Install the package ggplot2
#install.packages("ggplot2")
# Any time I want to use this package, I need to load it
library(ggplot2)
View(cars)
# A quick baseR plot - this is not ggplot
plot(cars)
# Our first ggplot
#We need data + aes + geom
ggplot(data = cars) +
aes(x = speed, y = dist) +
geom_point()
p <- ggplot(data = cars) +
aes(x = speed, y = dist) +
geom_point()
# Add a line geom with geom_line()
p + geom_line()
# Add a trend line close to the data
p + geom_smooth()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
p + geom_smooth(method = "lm")
## `geom_smooth()` using formula 'y ~ x'
# Adding labels
p + geom_smooth(method = "lm", se = FALSE) +
labs(title = "Speed and Stopping Distances of Cars",
x = "Speed (MPH)",
y = "Stopping Distance (ft)",
subtitle = "Your informative subtitle text here",
caption = "Dataset: 'cars'") +
theme_bw()
## `geom_smooth()` using formula 'y ~ x'
##
#Read in drug expression data
url <- "https://bioboot.github.io/bimm143_S20/class-material/up_down_expression.txt"
genes <- read.delim(url)
head(genes)
## Gene Condition1 Condition2 State
## 1 A4GNT -3.6808610 -3.4401355 unchanging
## 2 AAAS 4.5479580 4.3864126 unchanging
## 3 AASDH 3.7190695 3.4787276 unchanging
## 4 AATF 5.0784720 5.0151916 unchanging
## 5 AATK 0.4711421 0.5598642 unchanging
## 6 AB015752.4 -3.6808610 -3.5921390 unchanging
# How many genes
nrow(genes)
## [1] 5196
# Column names and number of columns
colnames(genes)
## [1] "Gene" "Condition1" "Condition2" "State"
ncol(genes)
## [1] 4
#How many upreglated genes
table(genes$State)
##
## down unchanging up
## 72 4997 127
#Fraction of genes up-regulated
round ( (table(genes$State) / nrow(genes)) * 100, 2)
##
## down unchanging up
## 1.39 96.17 2.44
# Let's make a first plot attempt
ggplot(data = genes) +
aes(x = Condition1, y = Condition2, col = State) +
geom_point()
#Change colors
ggplot(data = genes) +
aes(x = Condition1, y = Condition2, col = State) +
geom_point() +
scale_color_manual(values = c("blue", "gray", "red")) +
labs(title = "Gene Expression Changes Upon Drug Treatment",
x = "Control (no drug)",
y = "Drug Treatment") +
theme_bw()
##
#Optional Part 6
#install.packages("gapminder")
library(gapminder)
# File location online
url2 <- "https://raw.githubusercontent.com/jennybc/gapminder/master/inst/extdata/gapminder.tsv"
gapminder <- read.delim(url2)
#install.packages(dplyr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
gapminder_2007 <- gapminder %>%
filter(year == 2007)
ggplot(gapminder_2007) +
aes(x = gdpPercap, y = lifeExp, color = continent, size = pop) +
geom_point(alpha = 0.5)
# Color by pop
ggplot(gapminder_2007) +
aes(x = gdpPercap, y = lifeExp,
size = pop) +
geom_point(alpha = 0.5)
#Scale to reflect actual population differences
ggplot(gapminder_2007) +
geom_point(aes(x = gdpPercap, y = lifeExp,
size = pop),
alpha = 0.5) +
scale_size_area(max_size = 10)
#1957 Plot
gapminder_1957 <- gapminder %>%
filter(year == 1957)
ggplot(gapminder_1957) +
aes(x = gdpPercap, y = lifeExp,
color = continent,
size = pop) +
geom_point(alpha = 0.7)
scale_size_area(max_size = 10)
## <ScaleContinuous>
## Range:
## Limits: 0 -- 1
#Combine 1957 and 2007
gapminder_combined <- gapminder %>%
filter(year == 1957 | year == 2007)
ggplot(gapminder_combined) +
geom_point(aes(x = gdpPercap, y = lifeExp,
color=continent,
size = pop), alpha=0.7) +
scale_size_area(max_size = 10) +
facet_wrap(~year)
##
#Optional Part 7
gapminder_top5 <- gapminder %>%
filter(year == 2007) %>%
arrange(desc(pop)) %>%
top_n(5, pop)
gapminder_top5
## country continent year lifeExp pop gdpPercap
## 1 China Asia 2007 72.961 1318683096 4959.115
## 2 India Asia 2007 64.698 1110396331 2452.210
## 3 United States Americas 2007 78.242 301139947 42951.653
## 4 Indonesia Asia 2007 70.650 223547000 3540.652
## 5 Brazil Americas 2007 72.390 190010647 9065.801
#Creating a bar chart
ggplot(gapminder_top5) +
geom_col(aes(x = country, y = pop))
ggplot(gapminder_top5) +
geom_col(aes(x = country, y = lifeExp))
#Filling bars with color
ggplot(gapminder_top5) +
geom_col(aes(x = country, y = pop, fill = continent))
ggplot(gapminder_top5) +
geom_col(aes(x = country, y = pop, fill = lifeExp))
#Population size by country
ggplot(gapminder_top5) +
aes(x = country, y = pop, fill = gdpPercap) +
geom_col()
#Change order of bars
ggplot(gapminder_top5) +
aes(x = reorder(country, -pop), y=pop,
fill = gdpPercap) +
geom_col()
ggplot(gapminder_top5) +
aes(x = reorder(country, -pop), y = pop,
fill = country) +
geom_col(col = "gray30") +
guides(fill = FALSE)
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.
#Flipping bar charts
head(USArrests)
## Murder Assault UrbanPop Rape
## Alabama 13.2 236 58 21.2
## Alaska 10.0 263 48 44.5
## Arizona 8.1 294 80 31.0
## Arkansas 8.8 190 50 19.5
## California 9.0 276 91 40.6
## Colorado 7.9 204 78 38.7
USArrests$State <- rownames(USArrests)
ggplot(USArrests) +
aes(x = reorder(State, Murder), y = Murder) +
geom_col() +
coord_flip()
ggplot(USArrests) +
aes(x = reorder(State, Murder), y = Murder) +
geom_point() +
geom_segment(aes(x=State,
xend=State,
y=0,
yend=Murder),
color = "blue") +
coord_flip()
##
#Optional Part 8
#install.packages("gifski")
#install.packages("gganimate")
library(gapminder)
library(gganimate)
# Setup nice regular ggplot of the gapminder data
ggplot(gapminder, aes(gdpPercap, lifeExp, size = pop, colour = country)) +
geom_point(alpha = 0.7, show.legend = FALSE) +
scale_colour_manual(values = country_colors) +
scale_size(range = c(2, 12)) +
scale_x_log10() +
# Facet by continent
facet_wrap(~continent) +
# Here comes the gganimate specific bits
labs(title = 'Year: {frame_time}', x = 'GDP per capita', y = 'life expectancy') +
transition_time(year) +
shadow_wake(wake_length = 0.1, alpha = FALSE)
##
#Optional Part 9
#Combining Plots
#install.packages("patchwork")
library(patchwork)
# Setup some example plots
p1 <- ggplot(mtcars) + geom_point(aes(mpg, disp))
p2 <- ggplot(mtcars) + geom_boxplot(aes(gear, disp, group = gear))
p3 <- ggplot(mtcars) + geom_smooth(aes(disp, qsec))
p4 <- ggplot(mtcars) + geom_bar(aes(carb))
# Use patchwork to combine them here:
(p1 | p2 | p3) /
p4
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
sessionInfo()
## R version 4.1.2 (2021-11-01)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 10 x64 (build 19043)
##
## Matrix products: default
##
## locale:
## [1] LC_COLLATE=English_United States.1252
## [2] LC_CTYPE=English_United States.1252
## [3] LC_MONETARY=English_United States.1252
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.1252
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] patchwork_1.1.1 gganimate_1.0.7 dplyr_1.0.7 gapminder_0.3.0
## [5] ggplot2_3.3.5
##
## loaded via a namespace (and not attached):
## [1] Rcpp_1.0.8 plyr_1.8.6 pillar_1.6.4 compiler_4.1.2
## [5] jquerylib_0.1.4 highr_0.9 prettyunits_1.1.1 progress_1.2.2
## [9] tools_4.1.2 digest_0.6.27 lattice_0.20-45 nlme_3.1-155
## [13] evaluate_0.14 lifecycle_1.0.1 tibble_3.1.6 gtable_0.3.0
## [17] mgcv_1.8-38 pkgconfig_2.0.3 rlang_0.4.11 Matrix_1.4-0
## [21] DBI_1.1.2 yaml_2.2.1 xfun_0.29 withr_2.4.3
## [25] stringr_1.4.0 knitr_1.37 hms_1.1.1 generics_0.1.1
## [29] vctrs_0.3.8 grid_4.1.2 tidyselect_1.1.1 glue_1.6.0
## [33] R6_2.5.1 gifski_1.4.3-1 fansi_0.5.0 rmarkdown_2.11
## [37] tweenr_1.0.2 farver_2.1.0 purrr_0.3.4 magrittr_2.0.1
## [41] splines_4.1.2 scales_1.1.1 ellipsis_0.3.2 htmltools_0.5.1.1
## [45] assertthat_0.2.1 colorspace_2.0-2 labeling_0.4.2 utf8_1.2.2
## [49] stringi_1.7.6 munsell_0.5.0 crayon_1.4.2